Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3763 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.2584. Min Act: -0.0000

Data Index: 461131 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1075. Min Act: -0.0000

Data Index: 690468 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.3151. Min Act: -0.0000

Data Index: 1063934 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 3.3151. Min Range: -3.3151

Max Act: 2.5988. Min Act: -0.0000

Data Index: 225090 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 3.3151. Min Range: -3.3151

Max Act: 3.1444. Min Act: -0.0000

Data Index: 1106330 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 3.3151. Min Range: -3.3151

Max Act: 2.5867. Min Act: -0.0000

Data Index: 998542 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 3.3151. Min Range: -3.3151

Max Act: 2.6168. Min Act: -0.0000

Data Index: 70816 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 3.3151. Min Range: -3.3151

Max Act: 2.4051. Min Act: -0.0000

Data Index: 147536 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 3.3151. Min Range: -3.3151

Max Act: 2.4951. Min Act: -0.0000

Data Index: 1058565 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 3.3151. Min Range: -3.3151

Max Act: 2.4441. Min Act: -0.0000

Data Index: 736866 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 3.3151. Min Range: -3.3151

Max Act: 2.5308. Min Act: -0.0000

Data Index: 598217 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 3.3151. Min Range: -3.3151

Max Act: 2.7809. Min Act: -0.0000

Data Index: 526634 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 3.3151. Min Range: -3.3151

Max Act: 2.3764. Min Act: -0.0000

Data Index: 637633 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 3.3151. Min Range: -3.3151

Max Act: 2.3351. Min Act: -0.0000

Data Index: 1003327 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 3.3151. Min Range: -3.3151

Max Act: 2.3699. Min Act: -0.0000

Data Index: 542774 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 3.3151. Min Range: -3.3151

Max Act: 2.5051. Min Act: -0.0000

Data Index: 1486668 (Python Code)

Max Activating Token Index: 1006

Text #16

Max Range: 3.3151. Min Range: -3.3151

Max Act: 2.3418. Min Act: -0.0000

Data Index: 228020 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 3.3151. Min Range: -3.3151

Max Act: 2.4622. Min Act: -0.0000

Data Index: 1545974 (Python Code)

Max Activating Token Index: 558

Text #18

Max Range: 3.3151. Min Range: -3.3151

Max Act: 2.4634. Min Act: -0.0000

Data Index: 247860 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 3.3151. Min Range: -3.3151

Max Act: 2.4442. Min Act: -0.0000

Data Index: 539159 (C4 (Web Text))

Max Activating Token Index: 16